FaceParts: 高斯点分布的分割与编辑
FaceParts: Segmentation and Editing of Gaussian Splatting
AI总结：
本文提出FaceParts框架，用于无监督的高斯点分布头像分割与编辑，通过特征解耦、密度聚类和FLAME锚定部分转移实现精确编辑和跨头像部分交换。
摘要：
面部编辑是娱乐、虚拟现实和数字avatar中的重要任务。现有方法大多依赖于2D图像域的生成模型，而在3D领域通常通过劳动密集型的手动编辑完成。我们提出FaceParts，一个用于无监督分割和编辑高斯点分布头像的框架。与现有2D或网格辅助方法不同，我们的方法直接在高斯域中操作，将头像分解为语义连贯的面部部分。该方法整合了特征解耦、基于密度的聚类和FLAME锚定部分转移，实现了精确编辑和跨头像部分交换。在包含11个受试者的NeRSemble数据集上的实验表明，能够稳健地隔离如胡须、眉毛、眼睛和络腮胡等特征。定量评估证实，转移的段能够适应姿态和表情，同时保持身份一致性（ID = 0.943），低平均表情距离（AED = 0.021）和低平均姿态距离（APD = 0.004）。
英文摘要：
Facial editing is an important task with applications in entertainment, virtual reality, and digital avatars. Most existing approaches rely on generative models in the 2D image domain, while in 3D the task is typically performed through labor-intensive manual editing. We propose FaceParts, a framework for unsupervised segmentation and editing of Gaussian Splatting avatars. Unlike existing 2D or mesh-assisted methods, our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision. The method integrates feature disentanglement, density-based clustering, and FLAME-anchored part transfer, enabling precise editing and cross-avatar part swapping. Experiments on the NeRSemble dataset with 11 subjects demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
